Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/melodic-software/claude-code-plugins/design-handoffnpx skills add melodic-software/claude-code-plugins --skill design-handoffgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/melodic-software/claude-code-plugins/design-handoff)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/design-handoff"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/design-handoff.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00154 | $0.01198 |
| Opus 5 | $0.00077 | $0.00599 |
| Sonnet 5 | $0.00031 | $0.00240 |
| Haiku 4.5 | $0.00015 | $0.00120 |
Grade A, and why
design-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Current branch: !git branch --show-current 2>/dev/null || echo "unknown"
Purpose
The seam between design and planning. /planning:plan's prerequisite check blocks on design-gate evidence; this skill produces that evidence honestly. A binary check read off the artifact, then a handoff summary sourced from the artifacts rather than recalled from conversation memory.
Design artifacts live in <contract_dir>/<topic-slug>/design/ (default docs/topics/). The topic's contract slice on the task branch, joining the memory slice under contract_tier: local; roots, tier, and precedence resolve per the topic-docs binding ${CLAUDE_PLUGIN_ROOT}/reference/topic-docs.md. Derive <topic-slug> from the task or branch name (kebab-case, ≤40 chars; shared with /planning:design and /planning:plan).
Binary gate. Check the artifact, not your memory
Read design-threads.md in the topic's resolved design slice (<contract_dir>/<topic-slug>/design/, default docs/topics/; the memory slice under contract_tier: local) and confirm, thread by thread, that every design thread is one of:
- RESOLVED. The deciding rationale is recorded in the artifact (not merely "decided"), or
- directional. Direction agreed AND the remaining detail carries a research tag, or
- TAGGED-DEFERRED. An explicit research tag naming the external investigation needed.
A thread that is unresolved AND untagged is a silent gap → FAIL: list the offending thread(s), route back by invoking /planning:design via the Skill tool (its design-threads and discussion rounds) to resolve or tag, and do NOT hand off. This is a binary check read off design-threads.md, not a "did we cover enough?" recap. A producing model rubber-stamps its own recap, so the gate must be read off the file rather than judged from memory.
If design-threads.md does not exist, check for design-resolution.md at the same path (the /planning:design early-exit artifact). Early-exit slices hand off on that artifact alone. Neither present → FAIL: no design evidence; route back by invoking /planning:design via the Skill tool.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 59 lines · 154 tokens per session scan A 00de034173c8
design-handoff is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 1,198 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
build-priority-queue
For ordered processing: A search, Dijkstra, event simulation, task scheduling. Efficient min/max extraction with heap-based queue.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.
compose-small-helpers
For complex behavior: build from tiny functions, chain transformations, make code read like a pipeline of operations.
count-combinations
For probability and counting: permutations, combinations, sample spaces, Monte Carlo simulation, brute-force enumeration, card/dice problems.